Filters








7,570 Hits in 6.0 sec

An Evaluation of Anomaly Detection and Diagnosis in Multivariate Time Series

Astha Garg, Wenyu Zhang, Jules Samaran, Ramasamy Savitha, Chuan-Sheng Foo
2021 IEEE Transactions on Neural Networks and Learning Systems  
This article presents a systematic and comprehensive evaluation of unsupervised and semisupervised deep-learning-based methods for anomaly detection and diagnosis on multivariate time series data from  ...  In time-series anomaly detection, detecting anomalous events is more important than detecting individual anomalous time points.  ...  metrics for time series anomaly detection in terms of their robustness and ability to reward the detection of anomalous events.  ... 
doi:10.1109/tnnls.2021.3105827 pmid:34464278 fatcat:ffdg5hefpfb4lofm6iwx4lrhhe

A Deep Neural Network for Unsupervised Anomaly Detection and Diagnosis in Multivariate Time Series Data

Chuxu Zhang, Dongjin Song, Yuncong Chen, Xinyang Feng, Cristian Lumezanu, Wei Cheng, Jingchao Ni, Bo Zong, Haifeng Chen, Nitesh V. Chawla
2019 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
Anomaly detection and diagnosis in multivariate time series refer to identifying abnormal status in certain time steps and pinpointing the root causes.  ...  In this paper, we propose a Multi-Scale Convolutional Recurrent Encoder-Decoder (MSCRED), to perform anomaly detection and diagnosis in multivariate time series data.  ...  Acknowledgments Chuxu Zhang and Nitesh V.  ... 
doi:10.1609/aaai.v33i01.33011409 fatcat:t3bacgxxpbc4favwdnd5722qxi

A Deep Neural Network for Unsupervised Anomaly Detection and Diagnosis in Multivariate Time Series Data [article]

Chuxu Zhang, Dongjin Song, Yuncong Chen, Xinyang Feng, Cristian Lumezanu, Wei Cheng, Jingchao Ni, Bo Zong, Haifeng Chen, Nitesh V. Chawla
2018 arXiv   pre-print
Anomaly detection and diagnosis in multivariate time series refer to identifying abnormal status in certain time steps and pinpointing the root causes.  ...  In this paper, we propose a Multi-Scale Convolutional Recurrent Encoder-Decoder (MSCRED), to perform anomaly detection and diagnosis in multivariate time series data.  ...  Acknowledgments Chuxu Zhang and Nitesh V.  ... 
arXiv:1811.08055v1 fatcat:elremwlgorbtpd7ichsrvnb55e

StackVAE-G: An efficient and interpretable model for time series anomaly detection [article]

Wenkai Li, Wenbo Hu, Ting Chen, Ning Chen, Cheng Feng
2022 arXiv   pre-print
In this work, we propose a novel autoencoder-based model, named StackVAE-G that can significantly bring the efficiency and interpretability to multivariate time series anomaly detection.  ...  Combining these two modules, we introduce the stacking block-wise VAE (variational autoencoder) with GNN (graph neural network) model for multivariate time series anomaly detection.  ...  SMD is one of the largest public datasets currently available for evaluating multivariate time-series anomaly detection.  ... 
arXiv:2105.08397v2 fatcat:dhjzfcabjfafvod6vmaztd4fu4

GTAD: Graph and Temporal Neural Network for Multivariate Time Series Anomaly Detection

Siwei Guan, Binjie Zhao, Zhekang Dong, Mingyu Gao, Zhiwei He
2022 Entropy  
However, these multivariate time series anomaly detection algorithms do not take into account the correlation and time dependence between the sequences.  ...  The anomalous patterns of industrial production may be hidden by these time series. Previous LSTM-based and machine-learning-based approaches have made fruitful progress in anomaly detection.  ...  Acknowledgments: The authors would like to thank all anonymous reviewers and editors for their helpful suggestions for the improvement of this paper.  ... 
doi:10.3390/e24060759 pmid:35741480 pmcid:PMC9222957 fatcat:uqi2krnol5drpflbxp7qqe24ia

Mining Abnormal Patterns from Heterogeneous Time-Series with Irrelevant Features for Fault Event Detection [chapter]

Ryohei Fujimaki, Takayuki Nakata, Hidenori Tsukahara, Akinori Sato, Kenji Yamanishi
2008 Proceedings of the 2008 SIAM International Conference on Data Mining  
We address the issue of detecting fault events in multivariate time series.  ...  Key ideas in it include: 1) transforming the time-series for each feature into a sequence of anomaly scores, in order to map heterogeneous features to homogeneous features (an anomaly score indicates the  ...  In this paper, we address the issue of detecting fault events in multivariate time series which we must essentially monitor because we may not be able to detect a complex fault event from only a time-series  ... 
doi:10.1137/1.9781611972788.43 dblp:conf/sdm/FujimakiNTS08 fatcat:xtu5c2oolvbjhm3nwhth3sndq4

Mining abnormal patterns from heterogeneous time-series with irrelevant features for fault event detection

Ryohei Fujimaki, Takayuki Nakata, Hidenori Tsukahara, Akinori Sato, Kenji Yamanishi
2009 Statistical analysis and data mining  
We address the issue of detecting fault events in multivariate time series.  ...  Key ideas in it include: 1) transforming the time-series for each feature into a sequence of anomaly scores, in order to map heterogeneous features to homogeneous features (an anomaly score indicates the  ...  In this paper, we address the issue of detecting fault events in multivariate time series which we must essentially monitor because we may not be able to detect a complex fault event from only a time-series  ... 
doi:10.1002/sam.10030 fatcat:god3662ahrcxdkwzeevsmi6df4

Aortic coarctation: prognostic indicators of survival in the fetus

D Paladini
2004 Heart  
Of the 68 cases, 29 (42.7%) had an additional VSD and 10 (14.7%) a BAV, with 24/29 VSDs and 5/10 BAV detected prenatally. Extra-cardiac anomalies were associated in 27/68 cases (39.7%) (table 1 ).  ...  An abnormal karyotype was present in 20/57 cases in which it was known, which yields an aneuploidy rate of 35.1% (29.4% of the whole series) (table 1) .  ... 
doi:10.1136/hrt.2003.028696 pmid:15486145 pmcid:PMC1768525 fatcat:774ykvudbjaoda3227kiati6aa

Fault Detection and Diagnosis Using Combined Autoencoder and Long Short-Term Memory Network

Pangun Park, Piergiuseppe Di Marco, Hyejeon Shin, Junseong Bang
2019 Sensors  
In this paper, we propose an integrated learning approach for jointly achieving fault detection and fault diagnosis of rare events in multivariate time series data.  ...  It basically combines the strong low-dimensional nonlinear representations of the autoencoder for the rare event detection and the strong time series learning ability of LSTM for the fault diagnosis.  ...  Funding: This work was supported by research fund of Chungnam National University. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/s19214612 pmid:31652821 pmcid:PMC6866134 fatcat:mboe65xzkbakhgl5cp43folivq

On the feasibility of deploying cell anomaly detection in operational cellular networks

Gabriela Ciocarlie, Ulf Lindqvist, Kenneth Nitz, Szabolcs Novaczki, Henning Sanneck
2014 2014 IEEE Network Operations and Management Symposium (NOMS)  
In this paper, we build on our previous work [19] and study the feasibility of an operational deployment of an adaptive ensemble-method framework for modeling cell behavior.  ...  The Self-Organizing Networks (SON) concept includes the functional area known as self-healing, which aims to automate the detection and diagnosis of, and recovery from, network degradations and outages  ...  ACKNOWLEDGMENT We thank Lauri Oksanen, Kari Aaltonen, Richard Fehlmann, Christoph Frenzel, Péter Szilágyi, Michael Freed, and Christopher Connolly for their contributions.  ... 
doi:10.1109/noms.2014.6838305 dblp:conf/noms/CiocarlieLNNS14 fatcat:f5mbaqqq5bf25bgrxavagczllm

Robust Unsupervised Anomaly Detection with Variational Autoencoder in Multivariate Time Series Data

Umaporn Yokkampon, Abbe Mowshowitz, Sakmongkon Chumkamon, Eiji Hayashi
2022 IEEE Access  
Accurate detection of anomalies in multivariate time series data has attracted much attention due to its importance in a wide range of applications.  ...  in multivariate time series.  ...  Multivariate time series anomaly detection refers to anomaly detection of time series data with multiple sequences.  ... 
doi:10.1109/access.2022.3178592 fatcat:ombjjhtnerho5fovg3rs3ktaba

Detecting anomalies in cellular networks using an ensemble method

Gabriela F. Ciocarlie, Ulf Lindqvist, Szabolcs Novaczki, Henning Sanneck
2013 Proceedings of the 9th International Conference on Network and Service Management (CNSM 2013)  
This paper focuses on the problem of cell anomaly detection, addressing partial and complete degradations in cell-service performance, and it proposes an adaptive ensemble method framework for modeling  ...  The Self-Organizing Networks (SON) concept includes the functional area known as self-healing, which aims to automate the detection and diagnosis of, and recovery from, network degradations and outages  ...  ACKNOWLEDGMENT We thank Lauri Oksanen, Kari Aaltonen, Richard Fehlmann, Christoph Frenzel, Péter Szilágyi, Michael Freed, Ken Nitz, and Christopher Connolly for their contributions.  ... 
doi:10.1109/cnsm.2013.6727831 dblp:conf/cnsm/CiocarlieLNS13 fatcat:bco36v7o7zeorlcdw4hyymtsey

Research on Healthy Anomaly Detection Model Based on Deep Learning from Multiple Time-Series Physiological Signals

Kai Wang, Youjin Zhao, Qingyu Xiong, Min Fan, Guotan Sun, Longkun Ma, Tong Liu
2016 Scientific Programming  
features use multivariate Gauss distribution anomaly detection method to detect anomaly data.  ...  Our experiment is shown to have a significant performance in physiological signals anomaly detection.  ...  Then last, use multivariate Gaussian distribution to detect anomaly data in new unlabeled time-series physiological signals.  ... 
doi:10.1155/2016/5642856 fatcat:4f5lxxusi5aelmlaubrvzyfqve

An Attention-Based ConvLSTM Autoencoder with Dynamic Thresholding for Unsupervised Anomaly Detection in Multivariate Time Series

Tareq Tayeh, Sulaiman Aburakhia, Ryan Myers, Abdallah Shami
2022 Machine Learning and Knowledge Extraction  
in multivariate time series.  ...  As a substantial amount of multivariate time series data is being produced by the complex systems in smart manufacturing (SM), improved anomaly detection frameworks are needed to reduce the operational  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/make4020015 fatcat:e6vnwbtb4jdp3pqv5zyfn57j4e

Correlation-Based Anomaly Detection Method for Multi-sensor System

Han Li, Xinyu Wang, Zhongguo Yang, Sikandar Ali, Ning Tong, Samad Baseer, Le Sun
2022 Computational Intelligence and Neuroscience  
Then, a multi-sensor anomaly detection method, which finds and uses the correlation between features contained in the multidimensional time-series data, is proposed.  ...  That is, the method can effectively detect anomalies of multidimensional time series.  ...  Acknowledgments is work was supported by the National Natural Science Foundation of China (No. 61902051).  ... 
doi:10.1155/2022/4756480 pmid:35685153 pmcid:PMC9173954 fatcat:mhlssznh2vfk5izytj7xbz6kji
« Previous Showing results 1 — 15 out of 7,570 results